Functional Group Reasoning (Binary Classification) on FGBench Single
84.1AccuracyLFM2-2.6B-MMAI
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LFM2-2.6B-MMAITraining=ST, Reasoning=/no think2026.03 | 84.1 | 100 | |
| LFM2-2.6B-MMAITraining=MT, Reasoning=/think2026.03 | 84 | 100 | |
| LFM2-2.6B-MMAITraining=ST, Reasoning=/think2026.03 | 84 | 100 | |
| LFM2-2.6B-MMAITraining=MT, Reasoning=/no think2026.03 | 83.8 | 100 | |
| Opus-4-5Class=Proprietary LLM2026.03 | 76.1 | 100 | |
| GPT-5-2Class=Proprietary LLM2026.03 | 74.1 | 100 | |
| LFM2-2.6BClass=Liquid Foundation Model2026.03 | 74 | 100 | |
| GPT-5-1Class=Proprietary LLM2026.03 | 68.7 | 100 | |
| Llama-3.1Parameters=70B2026.03 | 68.3 | 100 | |
| Sonnet-4-5Class=Proprietary LLM2026.03 | 66.3 | 100 | |
| DeepSeek-3-2Class=Open-weight LLM2026.03 | 62.9 | 96.3 | |
| Qwen2.5-7BClass=Open-weight LLM2026.03 | 59 | 99.9 | |
| Llama-3.1Parameters=8B2026.03 | 54.8 | 99.3 | |
| LlaSMol-Mistral-7BClass=Foundational LLM for Chemistry2026.03 | 38.7 | 92.2 | |
| ChemLLM-7BClass=Foundational LLM for Chemistry2026.03 | 23.3 | 99.7 | |
| Llama-3-8B-MolInstClass=Foundational LLM for Chemistry2026.03 | 10.7 | 20.3 |